BlueBeck/

LlamaAligned-DeepSeekR1-Distill-70b

The aim of this model is to retain the reasoning capabilities of DeepSeek-R1-Distill-Llama-70B, while aligning more with the original Llama 3.3 model on which it is based.

As this model derives from Llama 3.3, the Llama 3.3 Community License Agreement applies.

Use the DeepSeek Chat Prompt Template when working with this model.

Use with transformers as you would Llama 3.3, but use the DeepSeek Chat Prompt Template as you would with the original DeepSeek-R1-Distill-Llama models.

Use these with Llama.cpp, LM Studio or Kobold.cpp. Thanks to mradermacher for converting these from the safetensors format.

Use with transformers as you would Llama 3.1, but use the DeepSeek Chat Prompt Template as you would with the original DeepSeek-R1-Distill-Llama models.

Use model id BlueBeck/LlamaAligned-DeepSeekR1-Distill-8b

Use these with Llama.cpp, LM Studio or Kobold.cpp. Thanks to mradermacher for converting these from the safetensors format.